Pedro Orvalho 🕵️‍♂️

Pedro Orvalho

(he/him)

Marie Skłodowska-Curie Postdoctoral Fellow

Artificial Intelligence Research Institute (IIIA), Spanish National Research Council (CSIC), Barcelona, Catalonia, Spain

Bio

I am a Marie Skłodowska-Curie (MSCA) Postdoctoral Fellow at the Artificial Intelligence Research Institute (IIIA), Spanish National Research Council (CSIC), collaborating with Felip Manyà. Previously, I was a MSCA COFUND Postdoctoral Fellow at the IIIA–CSIC, collaborating with Felip Manyà (IIIA-CSIC) and Guillem Alenyà (IRI-CSIC-UPC) on the ALLIES project.

Before joining IIIA-CSIC, I was a Postdoctoral Research Associate at the University of Oxford, contributing to the FUN2MODEL ERC project under the supervision of Marta Kwiatkowska.

I hold a Ph.D. in Computer Science from Instituto Superior Técnico (IST), Universidade de Lisboa (UL), completed as part of a European Doctorate Programme in collaboration with the Czech Technical University (CTU) in Prague.
My doctoral research was supervised by Vasco Manquinho and Mikoláš Janota, with research hosted at INESC-ID, IST (Lisbon), and CIIRC, CTU (Prague).

During the final year of my M.Sc. in Computer Science, I was a Research Assistant at Carnegie Mellon University (CMU), collaborating with Ruben Martins. I also gained some industry experience as a Research Intern at OutSystems, a leading Portuguese software company.

I am the proud recipient of several 🏆 awards and grants 🏆, including the Vencer o Adamastor 2025 prize, which recognizes innovative contributions by young scientists in Portugal, the ACM SIGSOFT Distinguished Paper Award at ESEC/FSE 2021, and the INESC-ID Best PhD Student Award.

📧 You can reach me at pmorvalho (AT) gmail.com 📧

Check out my CV!

Education

PhD in Computer Science

Instituto Superior Técnico, Universidade de Lisboa, in collaboration with the Czech Technical University (CTU) in Prague

MSc in Computer Science and Engineering

Instituto Superior Técnico, Universidade de Lisboa

BSc in Computer Science and Engineering

Instituto Superior Técnico, Universidade de Lisboa

Research Interests

Artificial Intelligence Automated Reasoning Neuro-symbolic AI Agentic AI Sofware Engineering AI4SE AI4Code Automated Verification Machine Learning Computer-aided Education Automated Program Repair Program Synthesis Program Analysis Fault Localisation Model-Based Diagnosis Formal Methods
Recent News

📄📄📄 3 Papers accepted @ FLoC 2026!! 🎉🎉🎉

Excited to share that three of our papers have been accepted at FLoC 2026, covering automated feedback for Prolog education, data-driven mutation testing for Prolog, and LLM-assisted MaxSAT modelling! 🎉

See all posts
👨‍💻 My Research 🕵️‍♂️

My research explores the synergy between Automated Reasoning (AR) and Machine Learning (ML), focusing on enhancing the robustness and reliability of ML Models (e.g., Large Language Models), across diverse reasoning tasks, including but not limited to code understanding.

By integrating the mathematical rigor and precision of formal methods with the scalability and adaptability of machine learning, I strive to develop AI systems that are both reliable and efficient, tackling critical challenges at the frontier of trustworthy AI.

I am always excited to explore new ideas together! 📧 Feel free to get in touch 📧 if you are interested in collaborating! 😃

Featured Publications
Solving MaxSAT Problems from Natural Language Descriptions with LLMs and PySAT featured image
Large Language Models

Solving MaxSAT Problems from Natural Language Descriptions with LLMs and PySAT

In this paper, we study a neuro-symbolic approach in which an LLM translates a natural language description of an optimisation problem into executable Python code using PySAT. The …

avatar
Pedro Orvalho
•
Read more
Can Automated Feedback Turn Students into Happy Prologians? featured image
Logic Programming

Can Automated Feedback Turn Students into Happy Prologians?

In this work, we present ProHelp, an automated assessment platform for Prolog built on top of the GitSEED framework, and we evaluate it through a survey of 144 students from a …

Ricardo Brancas
•
Read more
What Bugs Do Prolog Students Write? An Empirical Taxonomy and Data-Driven Mutation Framework featured image
Logic Programming

What Bugs Do Prolog Students Write? An Empirical Taxonomy and Data-Driven Mutation Framework

In this work, we present an empirical study of 7,201 Prolog submissions from 265 undergraduate students, from which we derive a fine-grained taxonomy of student bugs through manual …

Ricardo Brancas
•
Read more
See all
Recent & Upcoming Talks

From Brittle LLM Code Reasoning to MaxSAT-Based Verified Repairs @ UCL

In this talk, we examine the limitations of Large Language Models (LLMs) in semantic code reasoning, showing that their predictions may change under semantics-preserving code transformations, which suggests brittle rather than robust understanding of program semantics.

See all
Recent Publications
Pedro Orvalho, Marta Kwiatkowska, Guillem Alenyà, Felip Manyà (2026). Solving MaxSAT Problems from Natural Language Descriptions with LLMs and PySAT. In LLM-Solve @ FLoC 2026.
PDF project Preprint
Ricardo Brancas, Pedro Orvalho, Carolina Carreira, Vasco Manquinho, Ruben Martins (2026). Can Automated Feedback Turn Students into Happy Prologians?. In ICLP 2026.
PDF project Preprint DOI
Ricardo Brancas, Pedro Orvalho, Carolina Carreira, Vasco Manquinho, Ruben Martins (2026). What Bugs Do Prolog Students Write? An Empirical Taxonomy and Data-Driven Mutation Framework. In ICLP 2026.
project
Pedro Orvalho, Mikoláš Janota, Vasco Manquinho (2026). MENTOR: Fixing Introductory Programming Assignments With Formula-Based Fault Localization and LLM-Driven Program Repair. In JSS 2026.
PDF Code Dataset Project DOI
Pedro Orvalho, Marta Kwiatkowska (2026). PyVeritas: On Verifying Python via LLM-Based Transpilation and Bounded Model Checking for C. In P-AI-FM @ AAAI 2026.
project Preprint
Pedro Orvalho, Mikoláš Janota, Vasco Manquinho (2025). InvAASTCluster: On Applying Invariant-Based Program Clustering to Introductory Programming Assignments. In JSS 2025.
PDF Code Dataset Project Preprint DOI
See all